Integrated Energy Systems (IES) can dispatch multiple forms of energy jointly and can play an important role in participating in demand response. Aiming to solve the problem of optimizing energy management strategies for IES responding to Integrated Demand Response (IDR), this paper proposes a Deep Reinforcement Learning (DRL)-based scheduling strategy for IES under IDR. First, the IES framework is established based on the concept of the energy hub, while the incentive-based IDR strategy is introduced to exploit the potential schedulable electrical and thermal flexible resources, and the IES scheduling model is established to minimize the system operating cost. Second, the scheduling model is transformed into a Markov decision process, and a DRL algorithm based on deep deterministic policy gradient is used to reach the solution for the IES energy management strategy. Finally, the effectiveness of the proposed approach is validated by numerical examples.