A reinforcement learning approach to personalized learning recommendation systems

Xueying Tang, Yunxiao Chen, Xiaoou Li, Jingchen Liu, Zhiliang Ying

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Personalized learning refers to instruction in which the pace of learning and the instructional approach are optimized for the needs of each learner. With the latest advances in information technology and data science, personalized learning is becoming possible for anyone with a personal computer, supported by a data-driven recommendation system that automatically schedules the learning sequence. The engine of such a recommendation system is a recommendation strategy that, based on data from other learners and the performance of the current learner, recommends suitable learning materials to optimize certain learning outcomes. A powerful engine achieves a balance between making the best possible recommendations based on the current knowledge and exploring new learning trajectories that may potentially pay off. Building such an engine is a challenging task. We formulate this problem within the Markov decision framework and propose a reinforcement learning approach to solving the problem.

Original languageEnglish (US)
Pages (from-to)108-135
Number of pages28
JournalBritish Journal of Mathematical and Statistical Psychology
Volume72
Issue number1
DOIs
StatePublished - Feb 1 2019

Fingerprint

Recommendation System
Learning Systems
Reinforcement Learning
Learning
Engine
Recommendations
Personal Computer
Reinforcement (Psychology)
Information Technology
Data-driven
Microcomputers
Schedule
Optimise
Appointments and Schedules
Trajectory
Technology

Keywords

  • Markov decision
  • adaptive learning
  • personalized learning
  • reinforcement learning
  • sequential design

PubMed: MeSH publication types

  • Journal Article

Cite this

A reinforcement learning approach to personalized learning recommendation systems. / Tang, Xueying; Chen, Yunxiao; Li, Xiaoou; Liu, Jingchen; Ying, Zhiliang.

In: British Journal of Mathematical and Statistical Psychology, Vol. 72, No. 1, 01.02.2019, p. 108-135.

Research output: Contribution to journalArticle

Tang, Xueying ; Chen, Yunxiao ; Li, Xiaoou ; Liu, Jingchen ; Ying, Zhiliang. / A reinforcement learning approach to personalized learning recommendation systems. In: British Journal of Mathematical and Statistical Psychology. 2019 ; Vol. 72, No. 1. pp. 108-135.
@article{9666d6ea7cba4816b8f5cb1f217c2407,
title = "A reinforcement learning approach to personalized learning recommendation systems",
abstract = "Personalized learning refers to instruction in which the pace of learning and the instructional approach are optimized for the needs of each learner. With the latest advances in information technology and data science, personalized learning is becoming possible for anyone with a personal computer, supported by a data-driven recommendation system that automatically schedules the learning sequence. The engine of such a recommendation system is a recommendation strategy that, based on data from other learners and the performance of the current learner, recommends suitable learning materials to optimize certain learning outcomes. A powerful engine achieves a balance between making the best possible recommendations based on the current knowledge and exploring new learning trajectories that may potentially pay off. Building such an engine is a challenging task. We formulate this problem within the Markov decision framework and propose a reinforcement learning approach to solving the problem.",
keywords = "Markov decision, adaptive learning, personalized learning, reinforcement learning, sequential design",
author = "Xueying Tang and Yunxiao Chen and Xiaoou Li and Jingchen Liu and Zhiliang Ying",
year = "2019",
month = "2",
day = "1",
doi = "10.1111/bmsp.12144",
language = "English (US)",
volume = "72",
pages = "108--135",
journal = "British Journal of Mathematical and Statistical Psychology",
issn = "0007-1102",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - A reinforcement learning approach to personalized learning recommendation systems

AU - Tang, Xueying

AU - Chen, Yunxiao

AU - Li, Xiaoou

AU - Liu, Jingchen

AU - Ying, Zhiliang

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Personalized learning refers to instruction in which the pace of learning and the instructional approach are optimized for the needs of each learner. With the latest advances in information technology and data science, personalized learning is becoming possible for anyone with a personal computer, supported by a data-driven recommendation system that automatically schedules the learning sequence. The engine of such a recommendation system is a recommendation strategy that, based on data from other learners and the performance of the current learner, recommends suitable learning materials to optimize certain learning outcomes. A powerful engine achieves a balance between making the best possible recommendations based on the current knowledge and exploring new learning trajectories that may potentially pay off. Building such an engine is a challenging task. We formulate this problem within the Markov decision framework and propose a reinforcement learning approach to solving the problem.

AB - Personalized learning refers to instruction in which the pace of learning and the instructional approach are optimized for the needs of each learner. With the latest advances in information technology and data science, personalized learning is becoming possible for anyone with a personal computer, supported by a data-driven recommendation system that automatically schedules the learning sequence. The engine of such a recommendation system is a recommendation strategy that, based on data from other learners and the performance of the current learner, recommends suitable learning materials to optimize certain learning outcomes. A powerful engine achieves a balance between making the best possible recommendations based on the current knowledge and exploring new learning trajectories that may potentially pay off. Building such an engine is a challenging task. We formulate this problem within the Markov decision framework and propose a reinforcement learning approach to solving the problem.

KW - Markov decision

KW - adaptive learning

KW - personalized learning

KW - reinforcement learning

KW - sequential design

UR - http://www.scopus.com/inward/record.url?scp=85053382249&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053382249&partnerID=8YFLogxK

U2 - 10.1111/bmsp.12144

DO - 10.1111/bmsp.12144

M3 - Article

C2 - 30277574

AN - SCOPUS:85053382249

VL - 72

SP - 108

EP - 135

JO - British Journal of Mathematical and Statistical Psychology

JF - British Journal of Mathematical and Statistical Psychology

SN - 0007-1102

IS - 1

ER -