Unmanned aerial vehicle flight decision-making method based on meta-reinforcement learning parallel training algorithm

The invention provides an unmanned aerial vehicle flight decision-making method based on a meta-reinforcement learning parallel training algorithm. The unmanned aerial vehicle flight decision-making method comprises the steps of firstly constructing an unmanned aerial vehicle flight control model; then constructing a state space, an action space and a reward function of the flight decision of the unmanned aerial vehicle according to a Markov decision process; constructing a multi-task experience pool for storing element reinforcement learning algorithm training sample data; then defining meta reinforcement learning algorithm parameters and carrying out parallel training in multiple environments to realize an unmanned aerial vehicle meta reinforcement learning decision model; and finally, randomly initializing a new flight environment and an unmanned aerial vehicle state, testing an unmanned aerial vehicle flight decision model based on a meta reinforcement learning algorithm, and evaluating flight decision pe