# Learning to Acquire Information

arXiv: https://arxiv.org/abs/1704.06131 · HTML: https://mlsanity.com/paper/1704.06131/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2017.

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

- [Neural Program Synthesis with Query](https://mlsanity.com/paper/2205.07857/) (2022)
- [Online Symbolic Regression with Informative Query](https://mlsanity.com/paper/2302.10539/) (2023)
- [BRiG-AFA: Bellman Risk-to-Go Learning for Non-Myopic Active Feature Acquisition](https://mlsanity.com/paper/2608.02305/) (2026)
- [Wide Learning: Learning to Reach Evidence](https://mlsanity.com/paper/2608.29608/) (2026)

## Abstract (arXiv)

We consider the problem of diagnosis where a set of simple observations are used to infer a potentially complex hidden hypothesis. Finding the optimal subset of observations is intractable in general, thus we focus on the problem of active diagnosis, where the agent selects the next most-informative observation based on the results of previous observations. We show that under the assumption of uniform observation entropy, one can build an implication model which directly predicts the outcome of the potential next observation conditioned on the results of past observations, and selects the observation with the maximum entropy. This approach enjoys reduced computation complexity by bypassing the complicated hypothesis space, and can be trained on observation data alone, learning how to query without knowledge of the hidden hypothesis.