Abstract Video captioning is the task of automatically generating a textual description of the actions in a video. Although previous work (e.g. sequence-to-sequence model) has shown promising results in abstracting a coarse description of a short video, it is still very challenging to caption a video containing multiple fifine-grained actions with a detailed description. This paper aims to address the challenge by proposing a novel hierarchical reinforcement learning framework for video captioning, where a highlevel Manager module learns to design sub-goals and a low-level Worker module recognizes the primitive actions to fulfifill the sub-goal. With this compositional framework to reinforce video captioning at different levels, our approach signifificantly outperforms all the baseline methods on a newly introduced large-scale dataset for fifine-grained video captioning. Furthermore, our non-ensemble model has already achieved the state-of-the-art results on the widelyused MSR-VTT dataset