# Learning How to Self-Learn: Enhancing Self-Training Using Neural Reinforcement Learning

arXiv: https://arxiv.org/abs/1804.05734 · HTML: https://mlsanity.com/paper/1804.05734/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2018.

## Built on by (most cited first, 2 of 2)

- [Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems](https://mlsanity.com/paper/2108.12589/) (2021)
- [Cross-Language Speaker Attribute Prediction Using MIL and RL](https://mlsanity.com/paper/2601.04257/) (2026)

## Abstract (arXiv)

Self-training is a useful strategy for semi-supervised learning, leveraging raw texts for enhancing model performances. Traditional self-training methods depend on heuristics such as model confidence for instance selection, the manual adjustment of which can be expensive. To address these challenges, we propose a deep reinforcement learning method to learn the self-training strategy automatically. Based on neural network representation of sentences, our model automatically learns an optimal policy for instance selection. Experimental results show that our approach outperforms the baseline solutions in terms of better tagging performances and stability.