A multi-critic deep deterministic policy gradient UAV path planning

Abstract

Deep Deterministic Policy Gradient is a reinforcement learning method, which is widely used in unmanned aerial vehicle (UAV) for path planning. In order to solve the environmental sensitivity in path planning, we present an improved deep deterministic policy gradient for UAV path planning. Simulation results demonstrate that the algorithm improves the convergence speed, convergence effect and stability. The UAV can learn more knowledge from the complex environment.