A review of multi-agent reinforcement learning for multi-UAV [

Abstract

In recent years, single-agent Reinforcement Learning (RL)has achieved tremendous success in solving various sequential decision-making problems in machine learning. Some of these problems require more than one agent to resolve, so the notion Multi-agent Reinforcement Learning (MARL) has come to light. Unmanned Aerial Vehicle (UAV) technology became an attractive way to undertake several challenging applications, especially when Unmanned Aerial Vehicles (UAVs) form a swarm . One of the areas that sees great use of MARL is multi-UAV systems. In this work, we reviewed a number of articles that used these two concepts together MARL and swarm of UAVs.The objective is to minimize the search part for researchers who are more interested and educated in this feld .