# Combining Difficulty Ranking with Multi-Armed Bandits to Sequence Educational Content

arXiv: https://arxiv.org/abs/1804.05212 · HTML: https://mlsanity.com/paper/1804.05212/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2018.

## Built on by (most cited first, 6 of 6)

- [Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments](https://mlsanity.com/paper/2311.04528/) (2023)
- [Getting too personal(ized): The importance of feature choice in online adaptive algorithms](https://mlsanity.com/paper/2309.02856/) (2023)
- [EduQate: Generating Adaptive Curricula through RMABs in Education Settings](https://mlsanity.com/paper/2406.14122/) (2024)
- [Hierarchical Multi-Armed Bandits for the Concurrent Intelligent Tutoring of Concepts and Problems of Varying Difficulty Levels](https://mlsanity.com/paper/2408.07208/) (2024)
- [Prerequisite Structure Discovery in Intelligent Tutoring Systems](https://mlsanity.com/paper/2402.01672/) (2024)
- [MAB Optimizer for Estimating Math Question Difficulty via Inverse CV without NLP](https://mlsanity.com/paper/2508.19014/) (2025)

## Abstract (arXiv)

As e-learning systems become more prevalent, there is a growing need for them to accommodate individual differences between students. This paper addresses the problem of how to personalize educational content to students in order to maximize their learning gains over time. We present a new computational approach to this problem called MAPLE (Multi-Armed Bandits based Personalization for Learning Environments) that combines difficulty ranking with multi-armed bandits. Given a set of target questions MAPLE estimates the expected learning gains for each question and uses an exploration-exploitation strategy to choose the next question to pose to the student. It maintains a personalized ranking over the difficulties of question in the target set which is used in two ways: First, to obtain initial estimates over the learning gains for the set of questions. Second, to update the estimates over time based on the students responses. We show in simulations that MAPLE was able to improve students' learning gains compared to approaches that sequence questions in increasing level of difficulty, or rely on content experts. When implemented in a live e-learning system in the wild, MAPLE showed promising results. This work demonstrates the efficacy of using stochastic approaches to the sequencing problem when augmented with information about question difficulty.