To address the issue of reduced threat effectiveness in multi-UAV vs. single-target air combat, where existing strategies lack consideration for coordinated attacks, a reinforcement learning method based on a synchronous saturation strike strategy is proposed. The method designs a coordination metric function based on each UAV’s velocity and distance to the target, quantifying the expected performance of synchronized strikes. This metric is then integrated into the reward function of a reinforcement learning framework. Trained within the Deep Deterministic Policy Gradient (DDPG) framework, the resulting policy enables coordinated, saturated strikes by multiple UAVs against the target. Simulation results demonstrate that the proposed strategy significantly reduces the average loss rate and increases the win rate, confirming its effectiveness and superiority.