Abstract. In this paper, we propose a collaborative deep reinforcement learning (C-DRL) method for multi-object tracking. Most existing multiobject tracking methods employ the tracking-by-detection strategy which fifirst detects objects in each frame and then associates them across different frames. However, the performance of these methods rely heavily on the detection results, which are usually unsatisfified in many real applications, especially in crowded scenes. To address this, we develop a deep prediction-decision network in our C-DRL, which simultaneously detects and predicts objects under a unifified network via deep reinforcement learning. Specififically, we consider each object as an agent and track it via the prediction network, and seek the optimal tracked results by exploiting the collaborative interactions of difffferent agents and environments via the decision network.Experimental results on the challenging MOT15 and MOT16 benchmarks are presented to show the effffectiveness of our approach