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
Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Spaced repetition is a learning technique in which content to be learned or memorized is reviewed multiple times with gaps in between for efficient memorization and practice of skills. Two of the most common systems used for providing spaced repetition on e-learning platforms are Leitner and SuperMemo systems. Previous work has demonstrated that deep reinforcement learning (DRL) is able to give performance comparable to traditional benchmarks such as Leitner and SuperMemo in a flashcard based setting with simulated learning behaviour. In this work, our main contribution has been introduction of two new reward functions to be used by the DRL agent. The first, is a realistically observable reward function that uses the average of sum of outcomes in a sample of exercises. The second uses a Long Short Term Memory (LSTM) network as a form of reward shaping to predict the rewards to be used by DRL agent. Our results indicate that in both cases, DRL performs well. But, when LSTM based reward function is used, the DRL agent learns good policy smoother and faster. Also, the quality of the student-tutor interaction data used to train the LSTM network displays an effect on the performance of the DRL agent.

Abstract [sv]

Spaced repetition är en inlärningsteknik där innehåll som ska memoriseras upprepas med mellanrum flera gånger för att minnets styrka ska öka. Två av de vanligaste algoritmerna som används för att ge spaced repetition på digitala utbildningsplattformar är Leitner och SuperMemo. Tidigare arbete har visat att Deep Reinforcement Learning (DRL) för schemaläggning av spaced repetition kan ge inlärning likt traditionella algoritmer i en flashcard-baserad simulering av lärande studenter. I detta arbete är vårt huvudsakliga bidrag att introducera två nya belöningsfunktioner som används av DRL-agenten. Den första är en realistisk observerbar belöningsfunktion som använder medelvärdet av summan av resultat i ett prov av övningar. Den andra använder ett återkopplat neuralt nätverk (LSTM) som en form av reward-shaping för att räkna ut de belöningar som DRL-agenten ska belönas med. Våra resultat visar att DRL i fungerar bra i båda fallen. När LSTM-baserad belöningsfunktion används lär sig DRL-agenten en bra policy snabbare. Resultaten visar också att kvaliteten på student-interaktionsdata som används för att träna LSTM-nätverket har en stor effekt på DRLagentens prestanda.

Place, publisher, year, edition, pages
2019. , p. 82
Series
TRITA-EECS-EX ; 2019:217
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-253789OAI: oai:DiVA.org:kth-253789DiVA, id: diva2:1326042
External cooperation
Sana Labs AB
Supervisors
Examiners
Available from: 2019-06-20 Created: 2019-06-17 Last updated: 2019-06-20Bibliographically approved

Open Access in DiVA

fulltext(2748 kB)60 downloads
File information
File name FULLTEXT01.pdfFile size 2748 kBChecksum SHA-512
eb477fe2facf4b931d0e03d57e2662bbe1b94f0073673f331743d7a4e6184be613241de6660f52d95b58f76b4a99953104dee362fffe40a24b792ceef85186d8
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: 60 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: 217 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