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
Increasingly Complex Environments in Deep Reinforcement Learning
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Miljöer med ökande komplexitet i deep reinforcement learning (Swedish)
Abstract [en]

In this thesis, we used deep reinforcement learning to train autonomous agents and evaluated the impact of increasing the complexity of the training environment over time. This was compared to using a fixed complexity. Also, we investigated the impact of using a pre-trained agent as a starting point for training in an environment with a different complexity, compared to an untrained agent. The scope was limited to only training and analyzing agents playing a variant of the 2D game Snake. Random obstacles were placed on the map, and complexity corresponds to the amount of obstacles. Performance was measured in terms of eaten fruits.

The results showed benefits in overall performance for the agent trained in increasingly complex environments. With regard to previous research, it was concluded that this seems to hold generally, but more research is needed on the topic. Also, the results displayed benefits of using a pre-trained model as a starting point for training in a different complexity environment, which was hypothesized.

Abstract [sv]

I denna studie använde vi deep reinforcement learning för att träna autonoma agenter och utvärderade inverkan av att använda miljöer med ökande komplexitet över tid. Detta jämfördes med att använda en fixerad komplexitet. Utöver detta jämförde vi att använda en tränad agent som startpunkt för träning i en miljö med en annan komplexitet, jämfört med att använda en otränad agent. Studien avgränsades till att bara träna och analysera agenter på en variant av 2D-spelet Snake. Hinder placerades slumpmässigt ut på kartan, och komplexiteten motsvarar antalet hinder. Prestationen mättes i antal frukter som agenten lyckades äta.

Resultaten visade att agenten som tränades i miljöer med ökande komplexitet presterade bättre totalt sett. Med hänsyn till tidigare forskning drogs slutsatsen att detta verkar vara ett generellt fenomen, men att mer forskning behövs på ämnet. Vidare visade resultaten att det finns fördelar med att använda en redan tränad agent som startpunkt för träning i en miljö med en annan komplexitet, vilket var en del av författarnas hypotes.

Place, publisher, year, edition, pages
2019. , p. 33
Series
TRITA-EECS-EX ; 2019:384
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-259193OAI: oai:DiVA.org:kth-259193DiVA, id: diva2:1350714
Supervisors
Examiners
Available from: 2019-09-17 Created: 2019-09-12 Last updated: 2019-09-17Bibliographically approved

Open Access in DiVA

fulltext(913 kB)24 downloads
File information
File name FULLTEXT01.pdfFile size 913 kBChecksum SHA-512
2029f17031d799bbe0182031abf15c83961203a40d0e355f5b5dee05af7673db68a7e0737a989507b3ff273f867122639b9be28682d70abbe55f3d09eea8faba
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: 24 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: 76 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