# Discovering General-Purpose Active Learning Strategies

arXiv: https://arxiv.org/abs/1810.04114 · HTML: https://mlsanity.com/paper/1810.04114/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2018.

## Built on by (most cited first, 11 of 11)

- [Active Offline Policy Selection](https://mlsanity.com/paper/2106.10251/) (2021)
- [ImitAL: Learning Active Learning Strategies from Synthetic Data](https://mlsanity.com/paper/2108.07670/) (2021)
- [Deep reinforced active learning for multi-class image classification](https://mlsanity.com/paper/2206.13391/) (2022)
- [Performance-guided Reinforced Active Learning for Object Detection](https://mlsanity.com/paper/2601.15688/) (2026)
- [ImitAL: Learned Active Learning Strategy on Synthetic Data](https://mlsanity.com/paper/2208.11636/) (2022)
- [Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes](https://mlsanity.com/paper/2309.05477/) (2023)
- [Active Learning for Argument Mining: A Practical Approach](https://mlsanity.com/paper/2109.13611/) (2021)
- [Embodied Learning for Lifelong Visual Perception](https://mlsanity.com/paper/2112.14084/) (2021)
- [Aligning Data Selection with Performance: Performance-driven Reinforcement Learning for Active Learning in Object Detection](https://mlsanity.com/paper/2310.08387/) (2023)
- [Simulating, Fast and Slow: Learning Policies for Black-Box Optimization](https://mlsanity.com/paper/2406.04261/) (2024)
- [Survey of Active Learning Hyperparameters: Insights from a Large-Scale Experimental Grid](https://mlsanity.com/paper/2506.03817/) (2025)

## Abstract (arXiv)

We propose a general-purpose approach to discovering active learning (AL) strategies from data. These strategies are transferable from one domain to another and can be used in conjunction with many machine learning models. To this end, we formalize the annotation process as a Markov decision process, design universal state and action spaces and introduce a new reward function that precisely model the AL objective of minimizing the annotation cost. We seek to find an optimal (non-myopic) AL strategy using reinforcement learning. We evaluate the learned strategies on multiple unrelated domains and show that they consistently outperform state-of-the-art baselines.