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