This letter aims to develop a new learning-based flocking control framework that ensures inter-agent free collision. To achieve this goal, a leader-following flocking control based on a deep Q-network (DQN) is designed to comply with the three Reynolds’ flocking rules. However, due to the inherent conflict between the navigation attraction and inter-agent repulsion in the leader-following flocking scenario, there exists a potential risk of inter-agent collisions, particularly with limited training episodes. Failure to prevent such collision not only caused penalties in training but could lead to damage when the proposed control framework is executed on hardware. To address this issue, a control barrier function (CBF) is incorporated into the learning strategy to ensure collision-free flocking behavior. Moreover, the proposed learning framework with CBF enhances training efficiency and reduces the complexity of reward function design and tuning. Simulation results demonstrate the effectiveness and benefits of the proposed learning methodology and control framework.