# Bayesian Optimal Experimental Design for Simulator Models of Cognition

arXiv: https://arxiv.org/abs/2110.15632 · HTML: https://mlsanity.com/paper/2110.15632/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 29 Oct 2021.

## Builds on (most cited first, 7 of 7)

- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [Variational Bayesian Optimal Experimental Design](https://mlsanity.com/paper/1903.05480/) (2019)
- [Neural Approximate Sufficient Statistics for Implicit Models](https://mlsanity.com/paper/2010.10079/) (2020)
- [Bayesian Experimental Design for Implicit Models by Mutual Information Neural Estimation](https://mlsanity.com/paper/2002.08129/) (2020)
- [Sequential Bayesian Experimental Design for Implicit Models via Mutual Information](https://mlsanity.com/paper/2003.09379/) (2020)
- [Bayesian design of experiments for intractable likelihood models using coupled auxiliary models and multivariate emulation](https://mlsanity.com/paper/1803.07018/) (2018)

## Built on by (most cited first, 4 of 4)

- [Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist](https://mlsanity.com/paper/2606.26448/) (2026)
- [Designing Optimal Behavioral Experiments Using Machine Learning](https://mlsanity.com/paper/2305.07721/) (2023)
- [Amortised Experimental Design and Parameter Estimation for User Models of Pointing](https://mlsanity.com/paper/2307.09878/) (2023)
- [Identifying Informative Environments for Cognition Parameter Inference via Bayesian Experimental Design](https://mlsanity.com/paper/2607.28894/) (2026)

## Abstract (arXiv)

Bayesian optimal experimental design (BOED) is a methodology to identify experiments that are expected to yield informative data. Recent work in cognitive science considered BOED for computational models of human behavior with tractable and known likelihood functions. However, tractability often comes at the cost of realism; simulator models that can capture the richness of human behavior are often intractable. In this work, we combine recent advances in BOED and approximate inference for intractable models, using machine-learning methods to find optimal experimental designs, approximate sufficient summary statistics and amortized posterior distributions. Our simulation experiments on multi-armed bandit tasks show that our method results in improved model discrimination and parameter estimation, as compared to experimental designs commonly used in the literature.