In order to improve the resilience of distribution networks against typhoon disasters, a differentiated reinforcement method for distribution networks based on an improved proximal policy optimization (PPO) algorithm is proposed. First, the entire process from landing to departure of a typhoon is predicted based on the weather forecast information. And the probability of distribution networks lines fault is calculated. Then, a two-layer planning model is established with the goal of minimizing the annual investment cost, load loss cost, power outage loss and maintenance cost of different levels of line reinforcement. Finally, the improved PPO algorithm is used to obtain the differentiated reinforcement strategy of lines. The effectiveness of the proposed method is verified by the simulation case based on an improved IEEE 33-bus system.