The invention discloses a method for learning non-player character combat strategies on the basis of deep Q-learning networks. The method for learning the non-player character combat strategies on thebasis of the deep Q-learning networks has the advantages that the locations, skill cooling time and control states of learning non-player characters and locations, skill cooling time and control states of sparring characters are used as input states, all skills of the learning non-player characters are used as output action sets, the deep Q-learning networks are used as learning algorithms, bloodvolume difference information of the characters of two parties is used as reward for the deep Q-learning networks, the minimum time difference errors are used as targets, back propagation computationis carried out, and hidden layer weight coefficients and output layer weight coefficients of deep neural networks can be updated; the non-player character combat strategies can be automatically generated by the aid of the method, accordingly, the efficiency and the flexibility can be improved, the battle capacity can be reinforced, and the challenging and the interestingness of games can be obviously enhanced.