# Amortised Design Optimization for Item Response Theory

arXiv: https://arxiv.org/abs/2307.09891 · HTML: https://mlsanity.com/paper/2307.09891/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 19 Jul 2023.

## Builds on (most cited first, 8 of 8)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design](https://mlsanity.com/paper/2103.02438/) (2021)
- [On Nesting Monte Carlo Estimators](https://mlsanity.com/paper/1709.06181/) (2017)
- [Deep-IRT: Make Deep Learning Based Knowledge Tracing Explainable Using Item Response Theory](https://mlsanity.com/paper/1904.11738/) (2019)
- [Optimizing Sequential Experimental Design with Deep Reinforcement Learning](https://mlsanity.com/paper/2202.00821/) (2022)
- [Variational Item Response Theory: Fast, Accurate, and Expressive](https://mlsanity.com/paper/2002.00276/) (2020)
- [BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing](https://mlsanity.com/paper/2108.07386/) (2021)
- [Deep Reinforcement Learning for Adaptive Learning Systems](https://mlsanity.com/paper/2004.08410/) (2020)

## Abstract (arXiv)

Item Response Theory (IRT) is a well known method for assessing responses from humans in education and psychology. In education, IRT is used to infer student abilities and characteristics of test items from student responses. Interactions with students are expensive, calling for methods that efficiently gather information for inferring student abilities. Methods based on Optimal Experimental Design (OED) are computationally costly, making them inapplicable for interactive applications. In response, we propose incorporating amortised experimental design into IRT. Here, the computational cost is shifted to a precomputing phase by training a Deep Reinforcement Learning (DRL) agent with synthetic data. The agent is trained to select optimally informative test items for the distribution of students, and to conduct amortised inference conditioned on the experiment outcomes. During deployment the agent estimates parameters from data, and suggests the next test item for the student, in close to real-time, by taking into account the history of experiments and outcomes.