Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Blau, T., Bonilla, E.V., Chades, I., Dezfouli, A.: Optimizing sequential experimental design with deep reinforcement learning. In: International Conference on Machine Learning, pp. 2107ā2128. PMLR (2022)
Corbett, A.T., Anderson, J.R.: Knowledge tracing: Modeling the acquisition of procedural knowledge. User modeling and user-adapted interaction 4(4), 253ā278 (1994)
Foster, A., Ivanova, D.R., Malik, I., Rainforth, T.: Deep adaptive design: Amortizing sequential bayesian experimental design. In: International Conference on Machine Learning, pp. 3384ā3395. PMLR (2021)
Ghosh, A., Lan, A.: Bobcat: Bilevel optimization-based computerized adaptive testing. arXiv preprint arXiv:2108.07386 (2021)
Hambleton, R.K., Swaminathan, H.: Item Response Theory: Principles and Applications. Springer, Dordrecht (2013). https://doi.org/10.1007/978-94-017-1988-9
Li, X., Xu, H., Zhang, J., Chang, H.H.: Deep reinforcement learning for adaptive learning systems. J. Educ. Behav. Statist. 10769986221129847 (2020)
PaaĆen, B., Dywel, M., Fleckenstein, M., Pinkwart, N.: Sparse factor autoencoders for item response theory. In: Proceedings of the 15th International Conference on Educational Data Mining, p. 17 (2022)
Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: Reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1ā8 (2021). http://jmlr.org/papers/v22/20-1364.html
Rainforth, T., Cornish, R., Yang, H., Warrington, A., Wood, F.: On nesting monte carlo estimators. In: International Conference on Machine Learning, pp. 4267ā4276. PMLR (2018)
Rasch, G.: Probabilistic models for some intelligence and attainment tests. ERIC (1993)
Ryan, E.G., Drovandi, C.C., McGree, J.M., Pettitt, A.N.: A review of modern computational algorithms for Bayesian optimal design. Int. Statist. Rev. 84(1), 128ā154 (2016)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Smucker, B., Krzywinski, M., Altman, N.: Optimal experimental design. Nat. Methods 15(8), 559ā560 (2018)
Wu, M., Davis, R.L., Domingue, B.W., Piech, C., Goodman, N.: Variational item response theory: Fast, accurate, and expressive. arXiv preprint arXiv:2002.00276 (2020)
Yeung, C.K.: Deep-irt: Make deep learning based knowledge tracing explainable using item response theory. arXiv preprint arXiv:1904.11738 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Keurulainen, A., Westerlund, I., Keurulainen, O., Howes, A. (2023). Amortised Design Optimization forĀ Item Response Theory. In: Wang, N., Rebolledo-Mendez, G., Dimitrova, V., Matsuda, N., Santos, O.C. (eds) Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky. AIED 2023. Communications in Computer and Information Science, vol 1831. Springer, Cham. https://doi.org/10.1007/978-3-031-36336-8_56
Download citation
DOI: https://doi.org/10.1007/978-3-031-36336-8_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36335-1
Online ISBN: 978-3-031-36336-8
eBook Packages: Computer ScienceComputer Science (R0)