The challenging field of scene text detection requires complex data annotation, which is time-consuming and expensive. Techniques, such as weak supervision, can reduce the amount of data needed. In this paper we propose a weak supervision method for scene text detection, which makes use of reinforcement learning (RL). The reward received by the RL agent is estimated by a neural network, instead of being inferred from ground-truth labels. First, we enhance an existing supervised RL approach to text detection with several training optimizations, allowing us to close the performance gap to regression-based algorithms. We then use our proposed system in a weakly- and semi-supervised training on real-world data. Our results show that training in a weakly supervised setting is feasible. However, we find that using our model in a semi-supervised setting , e.g. when combining labeled synthetic data with unannotated real-world data, produces the best results.