Barth, Fabrício JailsonDamiani, Enrico FrancescoAbreu, Leonardo Duarte Malta deCarrete, Luis Filipe SanchezCastanares, Manuel2024-08-132024-08-132023https://repositorio.insper.edu.br/handle/11224/6780Projeto realizado para a empresa Embraer - Mentor na empresa: José Fernando Basso BrancalionThe aim of this project is to develop a reinforcement learning algorithm with its purpose being to find shipwrecked people using a swarm of drones. A simulated environment was also developed to train and visualize the outcome of the trained algorithm. This project does not discuss image recognition of shipwrecked people, since the true focus of this project is to optimize the search routine of a drone to find the target in the quickest way possible. The implemented Reinforce algorithm takes into account a dynamic map of probabilities, representing the chances of a person being found, as well as the position of other agents. Keywords: Multi-agent; Reinforcement learning, Shipwrecked people; Drone swarms.Digital49 p.enMulti-agentReinforcement learningShipwrecked peopleDrone swarmsSearch of shipwrecked people using drone swarms