A Method of UAV Formation Transformation Based on Reinforcement Learning Multi-agent

Abstract

AbstractIn the face of increasingly complex combat tasks and unpredictable combat environment, a single UAV can not meet the operational requirements, and UAVs perform tasks in a cooperative way. In this paper, an improved heuristic reinforcement learning algorithm is proposed to solve the formation transformation problem of multiple UAVs by using multi-agent reinforcement learning algorithm and heuristic function. With the help of heuristic back-propagation algorithm for formation transformation, the convergence efficiency of reinforcement learning is improved. Through the above reinforcement learning algorithm, the problem of low efficiency of formation transformation of multiple UAVs in confrontation environment is solved.