Unmanned chariot team firepower distribution method based on deep reinforcement learning

The invention relates to an unmanned chariot team firepower distribution method based on deep reinforcement learning, and belongs to the technical field of firepower distribution and deep reinforcement learning. According to the method, various factors such as combat tasks, battlefield situations, target threat degrees and target damage probabilities are comprehensively considered, the multi-roundfire distribution model of the unmanned combat vehicle team is established based on the MDP, the model is solved through the DQN algorithm, multi-round fire distribution of the unmanned combat vehicle team can be achieved through training. In the whole combat process, the firepower distribution model and parameters do not need to be manually adjusted any more, the unmanned chariot team determinesthe strike target of each round according to the battlefield situation, the robustness of firepower distribution decision making is improved, and the defects of an existing firepower distribution method are overcome. 本发明涉及一种基