In this paper, we propose an optimization framework for minimizing the delay of the user to access the file, by jointly optimizing the caching strategy, the trajectory design, and the transmit power of the unmanned aerial vehicle (UAV). However, the initial optimization problem is an NP-hard problem because of the unpredictability of the environment, e.g., the randomness of the content of the user’s requests and the changing location of the UAV. To circumvent this challenge, we first model the formulated optimization problem as a Markov decision process, and then propose a deep reinforcement learning (DRL) framework using the deep deterministic policy gradient (DDPG) algorithm for adaptive finding the optimal caching strategy, trajectory design, and transmit power of the UAV. Simulation results confirm the validity of the proposed algorithm.